K, Narsimlu; Das, Anweshan; Dubbelman, Gijs; (2023) A Stixel-Based Obstacle Avoidance System for Multi-Rover System. In: AIAA AVIATION 2023 Forum. American Institute of Aeronautics and Astronautics: San Diego, CA, USA and Online.

Preview

Text AIAA2023_3851001.pdf - Accepted Version Download (7MB) | Preview

Abstract

Autonomous driving is a very active research area, with virtually all major automotive manufacturers competing to bring the first autonomous car to the market. This race led to billions of dollars invested in developing novel sensors, processing platforms, and algorithms. In this paper, we explore the synergies between the challenges in self-driving technology and the development of navigation aids for autonomous robots. We aim to leverage the recently emerged methods for self-driving cars and use them to develop autonomous robots. In particular, we focus on perceiving the environment in real-time using stereo cameras. Then, as of proof-of-concept, we build a stereo perception framework for multi-robot systems based on a hardware platform used in the automotive industry. To perceive the environment, we adapt the implementation of the stixels algorithm. We discuss the challenges and modifications required for such an application domain transfer. Finally, we evaluate the framework on a cooperative automated vehicle research platform to show its usability in practice. The framework runs on a PC (x86_64 architecture) with a GPU card and the cooperative automated vehicle research platform with Drive PX2 (aarch64 architecture) compute platform.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as CSVXMLJSON

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item